ABSTRACT
PROBLEM: Diagnosing Autism Spectrum Disorder (ASD) remains a significant challenge, especially in regions where access to specialists is limited. Computer-based approaches offer a promising solution to make diagnosis more accessible. Eye tracking has emerged as a valuable technique in aiding the diagnosis of ASD. Typically, individuals' gaze patterns are monitored while they view videos designed according to established paradigms. In a previous study, we developed a method to classify individuals as having ASD or Typical Development (TD) by processing eye-tracking data using Random Forest ensembles, with a focus on a paradigm known as joint attention. AIM: This article aims to enhance our previous work by evaluating alternative algorithms and ensemble strategies, with a particular emphasis on the role of anticipation features in diagnosis. METHODS: Utilizing stimuli based on joint attention and the concept of "floating regions of interest" from our earlier research, we identified features that indicate gaze anticipation or delay. We then tested seven class balancing strategies, applied seven dimensionality reduction algorithms, and combined them with five different classifier induction algorithms. Finally, we employed the stacking technique to construct an ensemble model. RESULTS: Our findings showed a significant improvement, achieving an F1-score of 95.5%, compared to the 82% F1-score from our previous work, through the use of a heterogeneous stacking meta-classifier composed of diverse induction algorithms. CONCLUSION: While there remains an opportunity to explore new algorithms and features, the approach proposed in this article has the potential to be applied in clinical practice, contributing to increased accessibility to ASD diagnosis.
ABSTRACT
Cancer cachexia (CC) is a progressive metabolic syndrome that is marked by severe body weight loss. Metabolic disarrangement of fat tissues is a very early event in CC, followed by adipose tissue (AT) atrophy and remodelling. However, there is little information regarding the possible involvement of cellular turnover in this process. Thus, in this study, we evaluated the effect of CC on AT turnover and fibrosis of mesenteric (MEAT) and retroperitoneal (RPAT) adipose tissue depots as possible factors that contribute to AT atrophy. CC was induced by a subcutaneous injection of Walker tumour cells (2 × 107) in Wistar rats, and control animals received only saline. The experimental rats were randomly divided into four experimental groups: 0 days, 4 days, 7 days and 14 days after injection. AT turnover was analysed according to the Pref1/Adiponectin ratio of gene expression from the stromal vascular fraction and pro-apoptotic CASPASE3 and CASPASE9 from MEAT and RPAT. Fibrosis was verified according to the total collagen levels and expression of extracellular matrix genes. AT turnover was verified by measurements of lipolytic protein expression. We found that the Pref1/Adiponectin ratio was decreased in RPAT (81.85%, P < 0.05) with no changes in MEAT compared with the respective controls. CASPASE3 and CASPASE9 were activated on day 14 only in RPAT. Collagen was increased on day 7 in RPAT (127%) and MEAT (4.3-fold). The Collagen1A1, Collagen3A1, Mmp2 and Mmp9 mRNA levels were upregulated only in MEAT in CC. Lipid turnover was verified in RPAT and was not modified in CC. We concluded that the results suggest that CC affects RPAT cellular turnover, which may be determinant for RPAT atrophy.